It's implementation of Transformer in Attention is all you need. after 10 epoch receive BLUE score of 35.08
- python 3.5+
- pytorch 1.5
Before dive into transformer, I recommend you to watch Illustrated Guide to Transformers Neural Network: A step by step explanation, the best explanation that I found in the Internet.
- attention
- mask (source and target)
- encoder
- decoder
- inference